DrugAgent, a Planner-Instructor multi-agent LLM framework with drug-discovery documentation, beats ReAct by 4.92% ROC-AUC on DTI and exceeds general agents on two of three tasks in its Top3 variant.
J Code and Reproducibility The DrugAgent code is available at our anony- mous repository: https://anonymous.4open
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration
DrugAgent, a Planner-Instructor multi-agent LLM framework with drug-discovery documentation, beats ReAct by 4.92% ROC-AUC on DTI and exceeds general agents on two of three tasks in its Top3 variant.